From the corner of her eye, Emily could see the reflection of her face in the mirrored wall. The lines around her mouth seemed deeper than usual, her eyes tired. Trapped in the stale air, she kept picking at the chipped polish on her nails. It felt like a physical manifestation of her growing unease.

“This is ridiculous," she muttered, her voice barely audible.

Her coworker, Tom, looked at her, and she immediately felt the need to clarify. To apologize even. "I mean, the situation is ridiculous." The tone was off. She hated the sound of her own voice. She hated that she couldn't just *be* herself, without needing to justify everything.

Emotion: self-critical

Cluster: Shame / Guilt
PC1 (Valence): -1.66 Negative
PC2 (Disposition): 1.28

Role in Research

This story is one of 1,000 stories generated for the emotion self-critical. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 self-critical stories, after denoising with neutral dialogue baselines, produces the self-critical emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the self-critical vector is projected through the unembedding matrix.

Promoted:
L0.748
S0.662
ness0.425
ly0.374
0.351
Suppressed:
la-0.492
soon-0.304
(!)-0.301
secured-0.284
cautiously-0.280